Adaptive fast motion estimation based on probabilistic prediction and Object Grouping
Rajeev Ranjan, Piyush Mayank, Vijay Kumar, Somnath Sengupta · 2011
Conventional fast search motion estimation algorithms use a heuristically based approach to determine their search window. By making use of temporal correlation between the current frame and the past frame and spatial correlation between the neighborhood blocks, the proposed algorithm defines a search window on the basis of probabilistic prediction. Usage of Object Grouping results in an improved performance, when combined with probabilistic prediction.